Understanding RAFT: Adapting Language Models to Domain-Specific Retrieval Augmented Generation Introduction In the landscape of language models, pretraining on extensive corpora has become the st...

Introduction to LoRA and Full Fine-Tuning Fine-tuning LLMs like Llama-2, with billions of parameters, requires significant computational resources. Traditional full fine-tuning adjusts all the par...

Exploratory Data Analysis (EDA) on Token Length for Retriever-Augmented Generation (RAG) Pipelines Introduction Exploratory Data Analysis (EDA) is an essential step in the machine learning pipelin...

Re-ranker ColBERT re-ranker ColBERT is a technique that creates separate detailed multi-vector representations for both queries and documents. It then uses a soft and contextual approach to locat...

Tokenization The process of tokenization involves dividing a text or a string of characters into tokens. The most typical form of tokenization used in natural language processing is breaking down ...

Getting started with transformer models The AutoModel class is a tool used to create a model from a pre-existing checkpoint. This class is essentially a straightforward wrapper over a range of mod...

Exploring Techniques for Tuning Large Language Models (LLMs) As the field of artificial intelligence advances rapidly, it has become increasingly crucial to make the most of large language models ...

Using Transformers Pipeline functions Let’s see what happens when we use the sentiment analysis using the Pipeline function. from transformers import pipeline classifier = pipeline("sentiment-...

Transformers are language models All transformer models are language models trained on large amounts of raw text in a self-supervised fashion Not very useful for specific practical tasks => Tra...